This is an automated email from the ASF dual-hosted git repository.
dongjoon-hyun pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/spark-connect-swift.git
The following commit(s) were added to refs/heads/main by this push:
new 3f3bf17 [SPARK-57046] Support `truncateTable` in `Catalog`
3f3bf17 is described below
commit 3f3bf1730e4f07fb25a26329e8c3f0ab7ba1df88
Author: Dongjoon Hyun <[email protected]>
AuthorDate: Sun May 24 20:56:27 2026 -0700
[SPARK-57046] Support `truncateTable` in `Catalog`
### What changes were proposed in this pull request?
This PR aims to support `Spark_Connect_TruncateTable` message added in
Apache Spark Connect 4.2.0-preview5
- https://github.com/apache/spark/pull/55025
### Why are the changes needed?
For feature parity with Spark Connect.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Pass the CIs with the newly added test case.
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: Claude Opus 4.7
Closes #381 from dongjoon-hyun/SPARK-57046.
Authored-by: Dongjoon Hyun <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>
---
Sources/SparkConnect/Catalog.swift | 14 ++++++++++++++
Tests/SparkConnectTests/CatalogTests.swift | 19 +++++++++++++++++++
2 files changed, 33 insertions(+)
diff --git a/Sources/SparkConnect/Catalog.swift
b/Sources/SparkConnect/Catalog.swift
index a1420b7..a355efe 100644
--- a/Sources/SparkConnect/Catalog.swift
+++ b/Sources/SparkConnect/Catalog.swift
@@ -482,6 +482,20 @@ public actor Catalog: Sendable {
try await df.count()
}
+ /// Removes all rows from the table.
+ /// - Parameter tableName: A qualified or unqualified name that designates a
table.
+ /// If no database identifier is provided, it refers to a table in the
current database.
+ public func truncateTable(_ tableName: String) async throws {
+ let df = getDataFrame({
+ var truncateTable = Spark_Connect_TruncateTable()
+ truncateTable.tableName = tableName
+ var catalog = Spark_Connect_Catalog()
+ catalog.catType = .truncateTable(truncateTable)
+ return catalog
+ })
+ try await df.count()
+ }
+
/// Invalidates and refreshes all the cached data (and the associated
metadata) for any ``DataFrame``
/// that contains the given data source path. Path matching is by checking
for sub-directories,
/// i.e. "/" would invalidate everything that is cached and "/test/parent"
would invalidate
diff --git a/Tests/SparkConnectTests/CatalogTests.swift
b/Tests/SparkConnectTests/CatalogTests.swift
index a0cb287..0fb1343 100644
--- a/Tests/SparkConnectTests/CatalogTests.swift
+++ b/Tests/SparkConnectTests/CatalogTests.swift
@@ -503,6 +503,25 @@ struct CatalogTests {
await spark.stop()
}
+ @Test
+ func truncateTable() async throws {
+ let spark = try await SparkSession.builder.getOrCreate()
+ if await spark.version >= "4.2" {
+ let tableName = "TABLE_" + UUID().uuidString.replacingOccurrences(of:
"-", with: "")
+ try await SQLHelper.withTable(spark, tableName)({
+ try await spark.range(10).write.saveAsTable(tableName)
+ #expect(try await spark.table(tableName).count() == 10)
+ try await spark.catalog.truncateTable(tableName)
+ #expect(try await spark.table(tableName).count() == 0)
+ })
+
+ try await #require(throws: SparkConnectError.TableOrViewNotFound) {
+ try await spark.catalog.truncateTable("not_exist_table")
+ }
+ }
+ await spark.stop()
+ }
+
@Test
func refreshByPath() async throws {
let spark = try await SparkSession.builder.getOrCreate()
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
